Projected GANs Converge Faster

TL;DR

Projected GANs leverage a fixed pretrained feature space to significantly accelerate training convergence, improve image quality, and reduce computational costs, setting new benchmarks in image generation speed and quality.

Contribution

The paper introduces Projected GANs that project samples into a pretrained feature space and mix features across channels and resolutions to enhance training efficiency and image quality.

Findings

Achieves state-of-the-art FID scores on 22 datasets.

Converges up to 40 times faster than previous methods.

Reduces training time from 5 days to less than 3 hours.

Abstract

Generative Adversarial Networks (GANs) produce high-quality images but are challenging to train. They need careful regularization, vast amounts of compute, and expensive hyper-parameter sweeps. We make significant headway on these issues by projecting generated and real samples into a fixed, pretrained feature space. Motivated by the finding that the discriminator cannot fully exploit features from deeper layers of the pretrained model, we propose a more effective strategy that mixes features across channels and resolutions. Our Projected GAN improves image quality, sample efficiency, and convergence speed. It is further compatible with resolutions of up to one Megapixel and advances the state-of-the-art Fr\'echet Inception Distance (FID) on twenty-two benchmark datasets. Importantly, Projected GANs match the previously lowest FIDs up to 40 times faster, cutting the wall-clock time from 5 days to less than 3 hours given the same computational resources.